Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    references to social media, specifically Twitter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     moot
    -0.61
    vernment
    -0.61
     recomp
    -0.60
    anca
    -0.60
    itution
    -0.59
    rans
    -0.59
    pread
    -0.58
     999
    -0.58
    erella
    -0.58
    geries
    -0.58
    POSITIVE LOGITS
     (@
    0.86
     @
    0.76
     Username
    0.74
    Follow
    0.71
    edin
    0.71
    Newsletter
    0.71
    Subscribe
    0.71
    Tweet
    0.66
     HERE
    0.65
    lov
    0.65
    Act Density 0.039%

    No Known Activations